Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14686
    Prev
    Next
    INDEX
    Explanations

    references to successful or popular entities, such as hit songs, hit films, and hit TV series

    oai_token-act-pair · gpt-3.5-turbo

    references to successful movies or songs, specifically their popularity or success as "hits"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.70
    pires
    -0.69
    cia
    -0.69
    gemony
    -0.64
     horns
    -0.64
    otor
    -0.63
    ignt
    -0.62
    otype
    -0.62
    uth
    -0.61
    atu
    -0.59
    POSITIVE LOGITS
    achi
    0.89
    chens
    0.80
    ches
    0.76
     singles
    0.74
    dos
    0.72
    busters
    0.69
    phrase
    0.68
    ties
    0.68
    maker
    0.67
    casting
    0.67
    Activations Density 0.028%

    No Known Activations